© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11598
    Prev
    Next
    INDEX
    Explanations

    service quality and guarantees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¥åѦ
    -0.26
    Interpreter
    -0.21
    arrow
    -0.20
    çĶ±ä¸ŃåĽ½
    -0.19
    丰æĶ¶
    -0.19
    æ¢Ń
    -0.19
    agger
    -0.19
    æ±ĩ
    -0.18
    æįı
    -0.18
    çļĦä¼ĺåĬ¿
    -0.18
    POSITIVE LOGITS
    稼
    0.29
     guarantees
    0.27
    æī¿è¯º
    0.27
    æľįåĬ¡è´¨éĩı
    0.27
     guarantee
    0.27
    uptime
    0.26
    ä¿Ŀéļľ
    0.25
     metrics
    0.25
    æķħéļľ
    0.25
     performance
    0.24
    Activations Density 0.017%

    No Known Activations